mlsanityData to 14 Oct 2026

Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wild

arXiv 2309.08644 ↗First posted 15 Sep 2023cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

3D pose estimation is an invaluable task in computer vision with various practical applications. Especially, 3D pose estimation for multi-person from a monocular video (3DMPPE) is particularly challenging and is still largely uncharted, far from applying to in-the-wild scenarios yet. We pose three unresolved issues with the existing methods: lack of robustness on unseen views during training, vulnerability to occlusion, and severe jittering in the output. As a remedy, we propose POTR-3D, the first realization of a sequence-to-sequence 2D-to-3D lifting model for 3DMPPE, powered by a novel geometry-aware data augmentation strategy, capable of generating unbounded data with a variety of views while caring about the ground plane and occlusions. Through extensive experiments, we verify that the proposed model and data augmentation robustly generalizes to diverse unseen views, robustly recovers the poses against heavy occlusions, and reliably generates more natural and smoother outputs. The effectiveness of our approach is verified not only by achieving the state-of-the-art performance on public benchmarks, but also by qualitative results on more challenging in-the-wild videos. Demo videos are available at https://www.youtube.com/@potr3d.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 29 of its 45 references that are in the map. First posted on arXiv 15 Sep 2023.

Builds on

29 of 45 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  5. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 823
  6. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  7. 2020One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencingcited by 444
  8. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  9. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 272
  10. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  11. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  12. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
17 more
  1. 2019Learnable Triangulation of Human Posecited by 161
  2. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 159
  3. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 142
  4. 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 132
  5. 2017Compositional Human Pose Regressioncited by 124
  6. 2020Epipolar Transformerscited by 117
  7. 2019Single-Stage Multi-Person Pose Machinescited by 95
  8. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 89
  9. 2018Deep Cosine Metric Learning for Person Re-Identificationcited by 73
  10. 2021Direct Multi-view Multi-person 3D Pose Estimationcited by 64
  11. 2020Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representationcited by 57
  12. 2020SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimationcited by 52
  13. 2020HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimationcited by 44
  14. 2021Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networkscited by 16
  15. 2021Real-Time Multi-View 3D Human Pose Estimation using Semantic Feedback to Smart Edge Sensorscited by 16
  16. 2021Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Imagescited by 11
  17. 2022VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Datacited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 4; 2026: 4.

11 papers.

  1. 2024Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioningcited by 30
  2. 20233D Human Pose Perception from Egocentric Stereo Videoscited by 23
  3. 2025WorldPose: A World Cup Dataset for Global 3D Human Pose Estimationcited by 14
  4. 2026RAM: Recover Any 3D Human Motion in-the-Wildcited by 12
  5. 2025Bring Your Rear Cameras for Egocentric 3D Human Pose Estimationcited by 7
  6. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  7. 2025Every Angle Is Worth A Second Glance: Mining Kinematic Skeletal Structures from Multi-view Joint Cloudcited by 2
  8. 2026MuPPet: Multi-person 2D-to-3D Pose Liftingcited by 2
  9. 2025Multi-person Physics-based Pose Estimation for Combat Sportscited by 1
  10. 2026JRDB-Pose3D: A Multi-person 3D Human Pose and Shape Estimation Dataset for Roboticscited by 1
  11. 2026TSR-Ego: Temporally Guided Stereo Refinement Framework for Egocentric 3D Human Pose Estimationcited by 0